How fast sudoingX/dgx-spark-deepseek-v41 is gaining stars, and where it lands on Trendshift and GitHub Trending
Activity and trending
Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending
Oct 11 – Oct 26, 2026
Stars +45in 16 days
051015
14
Forks +3in 16 days
01
1
Merged PRs 0in 16 days
01
Trendshift Trendingwhere the repository ranked each day it made the top 25
Not in the Trendshift top 25 in this period
Oct 11Oct 13Oct 15Oct 17Oct 19Oct 21Oct 23Oct 25
The left and right arrow keys step from day to day; Home and End go to the first and the last
Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day
Stars gained
Forks gained
Merged PRs
Sun, Oct 11, 2026
+0
+0
0
Mon, Oct 12, 2026
+14
+0
0
Tue, Oct 13, 2026
+6
+0
0
Wed, Oct 14, 2026
+4
+0
0
Thu, Oct 15, 2026
+6
+1
0
Fri, Oct 16, 2026
+3
+0
0
Sat, Oct 17, 2026
+4
+1
0
Sun, Oct 18, 2026
+2
+0
0
Mon, Oct 19, 2026
+1
+0
0
Tue, Oct 20, 2026
+2
+0
0
Wed, Oct 21, 2026
+0
+0
0
Thu, Oct 22, 2026
+1
+0
0
Fri, Oct 23, 2026
+0
+1
0
Sat, Oct 24, 2026
+2
+0
0
Sun, Oct 25, 2026
+0
+0
0
Mon, Oct 26, 2026
+0
+0
0
Total
+45
+3
0
1#1 on the list
7Rank that day
Not trending
Social mentions
Recent discussions about this repository across the web
2 posts
two days later, i'm sold 🐋 that's hermes agent in the screenshot driving my local deepseek v4.1 on my 2x dgx sparks, 96k tokens deep into one session and still going strong i throw everything at it…
i've been running deepseek v4.1 flash on my 2x dgx sparks for about a week now and oh my dear lord this model is so so so much closer than you think don't judge it by its frontend capability, put it…
The fastest way to run DeepSeek V4.1 Flash on two DGX Sparks just dropped, and it came from @sudoingX . 141 tok/s on structured output. Decode that stays flat from 8k to 240k context. The default…
update! deepseek v4.1 flash just got faster at reading v1.1 of my 2x dgx spark recipe is out and the prompt side is up to 18% quicker 🐋 > 8k prompt, 1,763 tok/s → 2,090 tok/s prefill now > 32k…
i took deepseek v4.1 flash from 39 tok/s to 103.0 tok/s on 2x dgx sparks in under 4 days this is every step that moved it 🐋 > oct 8, the build i started on, 39 tok/s > oct 9, my own weights serving…
holy shit, i actually did it. deepseek v4.1 flash is flying on 2x dgx spark, serving with vllm 🐋 > structured output: 141.3 tok/s > code: 103.0 tok/s > prose: 58.3 tok/s this is the fastest vllm…
DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM kit, exact speculative decoding. Work in progress.
